{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T23:07:35Z","timestamp":1760828855131},"publisher-location":"Berlin, Heidelberg","reference-count":32,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642051807"},{"type":"electronic","value":"9783642051814"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-05181-4_4","type":"book-chapter","created":{"date-parts":[[2009,12,30]],"date-time":"2009-12-30T03:17:27Z","timestamp":1262143047000},"page":"65-84","source":"Crossref","is-referenced-by-count":54,"title":["Adaptive Optimal Feedback Control with Learned Internal Dynamics Models"],"prefix":"10.1007","author":[{"given":"Djordje","family":"Mitrovic","sequence":"first","affiliation":[]},{"given":"Stefan","family":"Klanke","sequence":"additional","affiliation":[]},{"given":"Sethu","family":"Vijayakumar","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Abbeel, P., Quigley, M., Ng, A.Y.: Using inaccurate models in reinforcement learning. In: Proc. Int. Conf. on Machine Learning (ICML), pp. 1\u20138 (2006)","DOI":"10.1145\/1143844.1143845"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Atkeson, C.G.: Randomly sampling actions in dynamic programming. In: Proc. Int. Symp. on Approximate Dynamic Programming and Reinforcement Learning, pp. 185\u2013192 (2007)","DOI":"10.1109\/ADPRL.2007.368187"},{"key":"4_CR3","first-page":"75","volume":"11","author":"C.G. Atkeson","year":"1997","unstructured":"Atkeson, C.G., Moore, A., Schaal, S.: Locally weighted learning for control. AI Review\u00a011, 75\u2013113 (1997)","journal-title":"AI Review"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Atkeson, C.G., Schaal, S.: Learning tasks from a single demonstration. In: Proc. Int. Conf. on Robotics and Automation (ICRA), Albuquerque, New Mexico, pp. 1706\u20131712 (1997)","DOI":"10.1109\/ROBOT.1997.614389"},{"key":"4_CR5","volume-title":"Dynamic programming and optimal control","author":"D.P. Bertsekas","year":"1995","unstructured":"Bertsekas, D.P.: Dynamic programming and optimal control. Athena Scientific, Belmont (1995)"},{"key":"4_CR6","unstructured":"Conradt, J., Tevatia, G., Vijayakumar, S., Schaal, S.: On-line learning for humanoid robot systems. In: Proc. Int. Conf. on Machine Learning (ICML), pp. 191\u2013198 (2000)"},{"issue":"1","key":"4_CR7","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/100.486658","volume":"3","author":"P.I. Corke","year":"1996","unstructured":"Corke, P.I.: A robotics toolbox for MATLAB. IEEE Robotics and Automation Magazine\u00a03(1), 24\u201332 (1996)","journal-title":"IEEE Robotics and Automation Magazine"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"D\u2019Souza, A., Vijayakumar, S., Schaal, S.: Learning inverse kinematics. In: Proc. Int. Conf. on Intelligence in Robotics and Autonomous Systems (IROS), Hawaii, pp. 298\u2013303 (2001)","DOI":"10.1109\/IROS.2001.973374"},{"key":"4_CR9","volume-title":"The Computational Theory of Optimal Control","author":"P. Dyer","year":"1970","unstructured":"Dyer, P., McReynolds, S.: The Computational Theory of Optimal Control. Academic Press, New York (1970)"},{"key":"4_CR10","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1523\/JNEUROSCI.05-07-01688.1985","volume":"5","author":"T. Flash","year":"1985","unstructured":"Flash, T., Hogan, N.: The coordination of arm movements: an experimentally confirmed mathematical model. Journal of Neuroscience\u00a05, 1688\u20131703 (1985)","journal-title":"Journal of Neuroscience"},{"issue":"1","key":"4_CR11","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1163\/156855308X291836","volume":"22","author":"M. Grebenstein","year":"2008","unstructured":"Grebenstein, M., van der Smagt, P.: Antagonism for a highly anthropomorphic hand-arm system. Advanced Robotics\u00a022(1), 39\u201355 (2008)","journal-title":"Advanced Robotics"},{"key":"4_CR12","volume-title":"Differential Dynamic Programming","author":"D.H. Jacobson","year":"1970","unstructured":"Jacobson, D.H., Mayne, D.Q.: Differential Dynamic Programming. Elsevier, New York (1970)"},{"key":"4_CR13","doi-asserted-by":"crossref","first-page":"353","DOI":"10.1007\/BF01185407","volume":"69","author":"M. Katayama","year":"1993","unstructured":"Katayama, M., Kawato, M.: Virtual trajectory and stiffness ellipse during multijoint arm movement predicted by neural inverse model. Biological Cybernetics\u00a069, 353\u2013362 (1993)","journal-title":"Biological Cybernetics"},{"key":"4_CR14","first-page":"623","volume":"9","author":"S. Klanke","year":"2008","unstructured":"Klanke, S., Vijayakumar, S., Schaal, S.: A library for locally weighted projection regression. Journal of Machine Learning Research\u00a09, 623\u2013626 (2008)","journal-title":"Journal of Machine Learning Research"},{"key":"4_CR15","unstructured":"Li, W.: Optimal Control for Biological Movement Systems. PhD dissertation, University of California, San Diego (2006)"},{"key":"4_CR16","unstructured":"Li, W., Todorov, E.: Iterative linear-quadratic regulator design for nonlinear biological movement systems. In: Proc. 1st Int. Conf. Informatics in Control, Automation and Robotics (2004)"},{"issue":"9","key":"4_CR17","doi-asserted-by":"publisher","first-page":"14391","DOI":"10.1080\/00207170701364913","volume":"80","author":"W. Li","year":"2007","unstructured":"Li, W., Todorov, E.: Iterative linearization methods for approximately optimal control and estimation of non-linear stochastic system. International Journal of Control\u00a080(9), 14391\u201314453 (2007)","journal-title":"International Journal of Control"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Nguyen-Tuong, D., Peters, J., Seeger, M., Schoelkopf, B.: Computed torque control with nonparametric regressions techniques. In: American Control Conference (2008)","DOI":"10.1109\/ACC.2008.4586493"},{"key":"4_CR19","volume-title":"Fundamentals of biomechanics: equilibrium, motion, and deformation","author":"N. \u00d6zkaya","year":"1991","unstructured":"\u00d6zkaya, N., Nordin, M.: Fundamentals of biomechanics: equilibrium, motion, and deformation. Van Nostrand Reinhold, New York (1991)"},{"key":"4_CR20","first-page":"983","volume-title":"The handbook of brain theory and neural networks","author":"S. Schaal","year":"2002","unstructured":"Schaal, S.: Learning Robot Control. In: The handbook of brain theory and neural networks, pp. 983\u2013987. MIT Press, Cambridge (2002)"},{"issue":"5","key":"4_CR21","doi-asserted-by":"crossref","first-page":"3208","DOI":"10.1523\/JNEUROSCI.14-05-03208.1994","volume":"14","author":"R. Shadmehr","year":"1994","unstructured":"Shadmehr, R., Mussa-Ivaldi, F.A.: Adaptive representation of dynamics during learning of a motor task. The Journal of Neurosciene\u00a014(5), 3208\u20133224 (1994)","journal-title":"The Journal of Neurosciene"},{"key":"4_CR22","volume-title":"The Computational Neurobiology of Reaching and Ponting","author":"R. Shadmehr","year":"2005","unstructured":"Shadmehr, R., Wise, S.P.: The Computational Neurobiology of Reaching and Ponting. MIT Press, Cambridge (2005)"},{"key":"4_CR23","volume-title":"Optimal control and estimation","author":"R.F. Stengel","year":"1994","unstructured":"Stengel, R.F.: Optimal control and estimation. Dover Publications, New York (1994)"},{"key":"4_CR24","unstructured":"Thrun, S.: Monte carlo POMDPs. In: Advances in Neural Information Processing Systems (NIPS), pp. 1064\u20131070 (2000)"},{"issue":"9","key":"4_CR25","doi-asserted-by":"publisher","first-page":"907","DOI":"10.1038\/nn1309","volume":"7","author":"E. Todorov","year":"2004","unstructured":"Todorov, E.: Optimality principles in sensorimotor control. Nature Neuroscience\u00a07(9), 907\u2013915 (2004)","journal-title":"Nature Neuroscience"},{"key":"4_CR26","doi-asserted-by":"publisher","first-page":"1226","DOI":"10.1038\/nn963","volume":"5","author":"E. Todorov","year":"2002","unstructured":"Todorov, E., Jordan, M.: Optimal feedback control as a theory of motor coordination. Nature Neuroscience\u00a05, 1226\u20131235 (2002)","journal-title":"Nature Neuroscience"},{"key":"4_CR27","first-page":"27","volume-title":"Advances in Neural Information Processing Systems (NIPS)","author":"E. Todorov","year":"2003","unstructured":"Todorov, E., Jordan, M.: A minimal intervention principle for coordinated movement. In: Advances in Neural Information Processing Systems (NIPS), pp. 27\u201334. MIT Press, Cambridge (2003)"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Todorov, E., Li, W.: A generalized iterative LQG method for locally-optimal feedback control of constrained nonlinear stochastic systems. In: Proc. of the American Control Conference (2005)","DOI":"10.1109\/ACC.2005.1469949"},{"key":"4_CR29","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1007\/BF00204593","volume":"61","author":"Y. Uno","year":"1989","unstructured":"Uno, Y., Kawato, M., Suzuki, R.: Formation and control of optimal trajectories in human multijoint arm movements: minimum torque-change model. Biological Cybernetics\u00a061, 89\u2013101 (1989)","journal-title":"Biological Cybernetics"},{"key":"4_CR30","doi-asserted-by":"publisher","first-page":"2602","DOI":"10.1162\/089976605774320557","volume":"17","author":"S. Vijayakumar","year":"2005","unstructured":"Vijayakumar, S., D\u2019Souza, A., Schaal, S.: Incremental online learning in high dimensions. Neural Computation\u00a017, 2602\u20132634 (2005)","journal-title":"Neural Computation"},{"issue":"1","key":"4_CR31","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1023\/A:1013258808932","volume":"12","author":"S. Vijayakumar","year":"2002","unstructured":"Vijayakumar, S., D\u2019Souza, A., Shibata, T., Conradt, J., Schaal, S.: Statistical learning for humanoid robots. Autonomous Robots\u00a012(1), 55\u201369 (2002)","journal-title":"Autonomous Robots"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Wolf, S., Hirzinger, G.: A new variable stiffness design: Matching requirements of the next robot generation. In: Proc. Int. Conf. on Robotics and Automation (ICRA), pp. 1741\u20131746 (2008)","DOI":"10.1109\/ROBOT.2008.4543452"}],"container-title":["Studies in Computational Intelligence","From Motor Learning to Interaction Learning in Robots"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-05181-4_4.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,23]],"date-time":"2020-11-23T21:49:05Z","timestamp":1606168145000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-05181-4_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642051807","9783642051814"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-05181-4_4","relation":{},"ISSN":["1860-949X","1860-9503"],"issn-type":[{"type":"print","value":"1860-949X"},{"type":"electronic","value":"1860-9503"}],"subject":[],"published":{"date-parts":[[2010]]}}}